Adversarial fine-tuning (i.e., training on adversarial perturbed inputs) has demonstrated promising results in improving the accuracy of natural language understanding tasks. However, the improved accuracy does not come for free but is accompanied by a significantly prolonged training time, limiting their applicability to larger and more complex models. This work revisits the efficiency-accuracy trade-off in adversarial fine-tuning by systematically analyzing if adversarial fine-tuning methods, in conjunction with several efficiency optimizations, are suitable for adapting pre-trained Transformer models for natural language understanding tasks. Our results show that multiple design choices are crucial in determining the efficiency-accuracy trade-off, and we introduce a method, ScaLA, that achieves better accuracy-vs-speed trade-off than prior methods. We show in experiments that our proposed method attains up to 14.7× adaptation speedups on BERT, RoBERTa, and T5, while achieving comparable accuracy to existing methods.

Deep and large pre-trained language models (e.g., BERT, GPT-3) are state-of-the-art for various natural language processing tasks. However, the huge size of these models brings challenges to fine-tuning and online deployment due to latency and cost constraints. Existing knowledge distillation methods reduce the model size, but they may encounter difficulties transferring knowledge from the teacher model to the student model due to the limited data from the downstream tasks. In this work, we propose AD^2, a novel and effective data augmentation approach to improving the task-specific knowledge transfer when compressing large pre-trained transformer models. Different from prior methods, AD^2 performs distillation by using an enhanced training set that contains both original inputs and adversarially perturbed samples that mimic the output distribution from the teacher. Experimental results show that this method allows better transfer of knowledge from the teacher to the student during distillation, producing student models that retain 99.6\% accuracy of the teacher model while outperforming existing task-specific knowledge distillation baselines by 1.2 points on average over a variety of natural language understanding tasks. Moreover, compared with alternative data augmentation methods, such as text-editing-based approaches, AD^2 is up to 28 times faster while achieving comparable or higher accuracy. In addition, when AD^2 is combined with more advanced task-agnostic distillation, we can advance the state-of-the-art performance even more. On top of the encouraging performance, this paper also provides thorough ablation studies and analysis. The discovered interplay between KD and adversarial data augmentation for compressing pre-trained Transformers may further inspire more advanced KD algorithms for compressing even larger scale models.

Robust tensor CP decomposition involves decomposing a tensor into low rank and sparse components. We propose a novel non-convex iterative algorithm with guaranteed recovery. It alternates between low-rank CP decomposition through gradient ascent (a variant of the tensor power method), and hard thresholding of the residual. We prove convergence to the globally optimal solution under natural incoherence conditions on the low rank component, and bounded level of sparse perturbations. We compare our method with natural baselines, which apply robust matrix PCA either to the \em flattened tensor, or to the matrix slices of the tensor. Our method can provably handle a far greater level of perturbation when the sparse tensor is block-structured. This naturally occurs in many applications such as the foreground-background separation task in videos. Our experiments validate these findings. Thus, we establish that tensor methods can tolerate a higher level of gross corruptions compared to matrix methods.

Tensor contractions constitute a key computational ingredient of numerical multi-linear algebra. However, as the order and dimension of tensors grow, the time and space complexities of tensor-based computations grow quickly. In this paper, we propose and evaluate new BLAS-like primitives that are capable of performing a wide range of tensor contractions on CPU and GPU efficiently. We begin by focusing on single-index contractions involving all the possible configurations of second-order and third-order tensors. Then, we discuss extensions to more general cases. Existing approaches for tensor contractions spend large amounts of time restructuring the data which typically involves explicit copy and transpose operations. In this work, we summarize existing approaches and present library-based approaches that avoid memory movement. Through systematic benchmarking, we demonstrate that our approach can achieve 10x speedup on a K40c GPU and 2x speedup on dual-socket Haswell-EP CPUs, using MKL and CUBLAS respectively, for small and moderate tensor sizes. This is relevant in many machine learning applications such as deep learning, where tensor sizes tend to be small, but require numerous tensor contraction operations to be performed successively. Concretely, we implement a Tucker decomposition and show that using our kernels yields atleast an order of magnitude speedup as compared to state-of-the-art libraries.